© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12771
    Prev
    Next
    INDEX
    Explanations

    words related to academic papers that manipulate language to analyze and interpret various subjects.

    oai_token-act-pair · gemini-2.0-flash

    scientific analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.57
    bigoplus
    -0.54
    पया
    -0.53
    Viited
    -0.51
    enderror
    -0.50
    ponses
    -0.49
    Datuak
    -0.49
     contextLoads
    -0.47
    QMetaType
    -0.47
    bigsqcup
    -0.46
    POSITIVE LOGITS
    webElementXpaths
    0.73
     démocr
    0.69
    rungsseite
    0.65
     varandra
    0.63
     élus
    0.59
     gouvernements
    0.59
     réfugi
    0.54
     ordinaires
    0.54
     buoni
    0.53
     hidrá
    0.52
    Activations Density 4.072%

    No Known Activations